Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mystilleef/spae-framework --skill spae-checkgit clone --depth 1 https://github.com/mystilleef/spae-frameworkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mystilleef/spae-framework/spae-check)<a href="https://agentmods.dev/skills/mystilleef/spae-framework/spae-check"><img src="https://agentmods.dev/badge/skills/mystilleef/spae-framework/spae-check.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01986 |
| Opus 5 | $0.00018 | $0.00993 |
| Sonnet 5 | $0.00007 | $0.00397 |
| Haiku 4.5 | $0.00004 | $0.00199 |
Grade C, and why
spae-check scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore-start --> How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check (SPAE)
When to use
STATE.jsonreportsphase: check.- Cursor names active task.
Goal
- Compare active task implementation against PLAN.md Intent, Acceptance, and Verification.
- Route gaps to /fix or advance clear task.
Input
Read:
.spae/current/STATE.json(consultreferences/STATE.mdfor field reference, directives, and phase snapshots)- Active task section from
.spae/current/PLAN.md(Intent,Acceptance,Verification) - Source files and test logs scoped to active task
Workflow
- GATE—Read
.spae/current/STATE.json; confirmphase: checkandactive_task_id. Self-heal state drift: iftasks[active_task_id]reads"todo", correct it to"in_progress"and writeSTATE.jsonbefore proceeding. Halt on state drift: iftasks[active_task_id]reads"done", halt. Read activePLAN.mdtask section; confirm title,Intent,Acceptance,Verification. Halt on missing or malformed input; report and make no changes. - ORIENT—Verify active task; hand off to
/fix,/build, or/verify. Leave source, tests,config, docs,PLAN.md,SPEC.md, task scope, andworkstreamcompletion untouched. - PLAN—List active-task
Acceptanceoutcomes andVerificationsteps. Map evidence for declaredIntent; scope source/test reads to active task. Never readSPEC.md. - ACT—Execute:
- Run active-task verification steps and project checks. Without automation, inspect source, logs, or scripted probes for observable behavior.
- Confirm every
Acceptanceoutcome andIntentagainst evidence. - Label findings with exactly two tags:
- Gap: unmet
Acceptance, failedVerification,Intentmismatch, speculative abstraction, unrequested complexity, defensive bloat beyond taskScope, or a self-introduced cleanup violation perreferences/cleanup-guide.md. Include unmet item, file:line, expected vs actual, reproducible evidence. Blocks a clear result. - Observation: minor concern outside task scope,
unrequestededge-case coverage, theoretical risk. Report only; never write toFIX.mdor affect the verdict.
- Gap: unmet
- Draft gaps per
references/FIX.mdschema; consultreferences/prose-protocol.md.
- VERIFY—Reconcile every
Acceptance,Verification, andIntentagainst evidence. Clear verdict only with zero gaps. Confirm draftedFIX.mdmatchesreferences/FIX.mdstructure. - PERSIST—Apply one verdict:
- Gap found: create/overwrite
.spae/current/FIX.mdperreferences/FIX.md. WriteSTATE.json:phase: fix; preserve status, cursor, task registry, version, workstream. Active task staysin_progress. - Task clear, tasks remain: write
STATE.json: mark active taskdone, advance cursor to next"todo"task,phase: build. - Final task clear: write
STATE.json: mark active taskdone, retain cursor active task ID,phase: verify. - All branches: re-read
STATE.jsonafter writing; on a field mismatch, rewrite and re-read beforeREPORT.
- Gap found: create/overwrite
- REPORT—Emit result per directives. Template B after gap, D after clear nonfinal task, E after clear final task. Observations under Findings only.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 207 lines · 37 tokens per session scan C 44577ef785be
spae-check is a skill published in the GitHub repository mystilleef/spae-framework (1 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,986 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ahk-test
Design, write, and run behavior-focused tests for an objective or existing code. Writes test files only and reports evidence. No tasks created, no harness tracking.
exploit-xss
Cross-site scripting (XSS) vulnerability detection and exploitation. Supports reflected XSS, stored XSS, DOM-based XSS, and blind XSS testing. Use this skill when user mentions XSS, cross-site scripting, script injection, or needs to test JavaScript injection in parameters, forms, headers, or DOM sources.
auto-verify
Verify completed plan against acceptance criteria. Use after all slices are executed.
superpowers
Always-on. The main development method: Plan → TDD → Implement → Verify → Report. Use for ANY non-trivial task. Do not write code without a plan and a test. Complex tasks (>3 files) → split into atomic tasks. Bug fix → Prove-It Pattern (reproduce with a test before the fix).
test-driven-development
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
testing-discipline
Use when the user wants to: add/fix tests, understand what is covered, determine whether something is "done", reproduce a bug with a test, check limits/rate-limit/failures, or when tests are written against a real DB/network. Covers: isolation from the prod store, domain-first tests, test names as a spec, boundary…